Backdoor Attacks against Deep Neural Networks by Personalized Audio Steganography

Liu, Peng; Zhang, Shuyi; Yao, Chuanjian; Ye, Wenzhe; Li, Xianxian

doi:10.1109/icpr56361.2022.9956521

Cited by 4 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, Zhai et al, [20], proposed a clustering-based backdoor attack that targeted speaker verification. The authors in [37] proposed an audio steganography-based personalized trigger for backdoor attacks on speaker verification systems. In this study, we focus (Figure 1) solely on backdoor attacks using model training data poisoning [38], [39], in which attackers can only manipulate training samples without having any information about the victim's model.…”

Section: Related Workmentioning

confidence: 99%

A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks

Mengara

2024

IEEE Access

View full text Add to dashboard Cite

Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault, attackers can train the DNN model using poisoned data, potentially degrading its performance. Another type of data poisoning attack that is extremely relevant to our investigation is label flipping, in which the attacker manipulates the labels for a subset of data. It has been demonstrated that these assaults may drastically reduce system performance, even for attackers with minimal abilities. In this study, we propose a backdoor attack named "DirtyFlipping", which uses dirty label techniques, 'label-on-label', to input triggers (clapping) in the selected data patterns associated with the target class, thereby enabling a stealthy backdoor.INDEX TERMS Poisoning attacks, Backdoor attacks, Adversarial machine learning.

show abstract

Section: Related Workmentioning

confidence: 99%

A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks

Mengara

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research Directions

Mengara,

Avila,

Falk

2024

IEEE Access

View full text Add to dashboard Cite

Deep neural network (DNN) classifiers are potent instruments that can be used in various security-sensitive applications. Nonetheless, they are vulnerable to certain attacks that impede or distort their learning process. For example, backdoor attacks involve polluting the DNN learning set with a few samples from one or more source classes, which are then labelled as a target class set by an attacker. Even if the DNN is trained on clean samples with no backdoors, this attack will still be successful if a backdoor pattern exists in the training data. Backdoor attacks are difficult to spot and can be used to make the DNN behave maliciously depending on the target selected by the attacker. In this study, we survey the literature and highlight the latest advances in backdoor attack strategies and defense mechanisms. We finalize the discussion on challenges and open issues, as well as future research opportunities.

show abstract

Backdoor Attacks against Voice Recognition Systems: A Survey

Yan,

Lan,

Yan

2024

ACM Comput. Surv.

View full text Add to dashboard Cite

Voice Recognition Systems (VRSs) employ deep learning for speech recognition and speaker recognition. They have been widely deployed in various real-world applications, from intelligent voice assistance to telephony surveillance and biometric authentication. However, prior research has revealed the vulnerability of VRSs to backdoor attacks, which pose a significant threat to the security and privacy of VRSs. Unfortunately, existing literature lacks a thorough review on this topic. This paper fills this research gap by conducting a comprehensive survey on backdoor attacks against VRSs. We first present an overview of VRSs and backdoor attacks, elucidating their basic knowledge. Then we propose a set of evaluation criteria to assess the performance of backdoor attack methods. Next, we present a comprehensive taxonomy of backdoor attacks against VRSs from different perspectives and analyze the characteristic of different categories. After that, we comprehensively review existing attack methods and analyze their pros and cons based on the proposed criteria. Furthermore, we review classic backdoor defense methods and generic audio defense techniques. Then we discuss the feasibility of deploying them on VRSs. Finally, we figure out several open issues and further suggest future research directions to motivate the research of VRSs security.

show abstract

Backdoor Attacks against Deep Neural Networks by Personalized Audio Steganography

Cited by 4 publications

References 12 publications

A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks

A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks

Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research Directions

Backdoor Attacks against Voice Recognition Systems: A Survey

Contact Info

Product

Resources

About